{"id":"W4241644272","doi":"10.3115/1604683.1604688","title":"Comparing corpora and lexical ambiguity","year":2000,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Fonds De La Recherche Scientifique - FNRS; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Ambiguity; Computer science; Domain (mathematical analysis); Newspaper; Natural language processing; Artificial intelligence; Information retrieval; Programming language; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01998393,0.0008181366,0.001096942,0.0135546,0.002254684,0.006962721,0.00166538,0.001591209,0.00502201],"category_scores_gemma":[0.149724,0.000630472,0.0008605804,0.01686657,0.002128921,0.006782485,0.004032945,0.0009898334,0.001401367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00138334,"about_ca_system_score_gemma":0.0009560502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177028,"about_ca_topic_score_gemma":0.003181021,"domain_scores_codex":[0.9631146,0.02192784,0.003456591,0.002372505,0.008537349,0.0005911996],"domain_scores_gemma":[0.8341537,0.1324222,0.005475581,0.01364471,0.01342369,0.000880125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003363662,0.001117543,0.1472882,0.006160894,0.002366103,0.001964364,0.009941094,0.0286959,0.01942514,0.09064774,0.02982092,0.6592084],"study_design_scores_gemma":[0.001034521,0.003020745,0.2388625,0.00373475,0.002830883,0.00838761,0.02085181,0.07627233,0.05338242,0.1715051,0.4191898,0.0009274247],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6865314,0.03237846,0.1536734,0.002371458,0.002702387,0.00152316,0.00974698,0.002767274,0.1083055],"genre_scores_gemma":[0.8190464,0.00678685,0.1468354,0.0008459228,0.0008945464,0.001902904,0.01819313,0.001132371,0.004362522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01998393,"threshold_uncertainty_score":0.1056864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02531234140263388,"score_gpt":0.2696550163850276,"score_spread":0.2443426749823937,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}